Instructions to use 1rsh/Qwen2.5-3B-SLMJ-binary-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 1rsh/Qwen2.5-3B-SLMJ-binary-GRPO with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="1rsh/Qwen2.5-3B-SLMJ-binary-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("1rsh/Qwen2.5-3B-SLMJ-binary-GRPO")
model = AutoModelForCausalLM.from_pretrained("1rsh/Qwen2.5-3B-SLMJ-binary-GRPO", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 1rsh/Qwen2.5-3B-SLMJ-binary-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "1rsh/Qwen2.5-3B-SLMJ-binary-GRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "1rsh/Qwen2.5-3B-SLMJ-binary-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/1rsh/Qwen2.5-3B-SLMJ-binary-GRPO

SGLang

How to use 1rsh/Qwen2.5-3B-SLMJ-binary-GRPO with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "1rsh/Qwen2.5-3B-SLMJ-binary-GRPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "1rsh/Qwen2.5-3B-SLMJ-binary-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "1rsh/Qwen2.5-3B-SLMJ-binary-GRPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "1rsh/Qwen2.5-3B-SLMJ-binary-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use 1rsh/Qwen2.5-3B-SLMJ-binary-GRPO with Docker Model Runner:
```
docker model run hf.co/1rsh/Qwen2.5-3B-SLMJ-binary-GRPO
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Thank you for your interest in this model, please provide us a few details. We are starting a synthetic data generation company and hence would like you to suggest domains for which we can release datasets.

Uploaded model

Developed by: 1rsh
License: apache-2.0
Finetuned from model : unsloth/qwen2.5-3b-instruct

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: -

Collection including 1rsh/Qwen2.5-3B-SLMJ-binary-GRPO

TinyJudge | Small Language Model as a Judge

Collection

12 items • Updated Apr 19, 2025